Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
Happy 83a6dcaa3e | 1 year ago | |
---|---|---|
.. | ||
README.md | 1 year ago | |
actor.py | 1 year ago | |
atari_agent.py | 1 year ago | |
atari_model.py | 1 year ago | |
impala_config.py | 1 year ago | |
requirements.txt | 1 year ago | |
train.py | 1 year ago |
Based on PARL, the IMPALA algorithm of deep reinforcement learning is reproduced, and the same level of indicators of the paper is reproduced in the classic Atari game.
Paper: IMPALA in Impala: Scalable distributed deep-rl with importance weighted actor-learner architectures
Please see here to know more about Atari games.
Learning curve with one learner (in a P40 GPU) and 32 actors (in 32 CPUs).
PongNoFrameskip-v4: mean_episode_rewards can reach 18-19 score in about 10 minutes.
Learning curves (mean_episode_rewards) of other games in an hour.
At first, We can start a local cluster with 32 CPUs:
xparl start --port 8010 --cpu_num 32
Note that it is not necessary to run the command each time before training.
We can reuse the xparl cluster for distributed training if we have started it before.
documentation
Then we can start the distributed training by running:
python train.py
PARL 是一个高性能、灵活的强化学习框架
Python C++ JavaScript Shell Markdown other
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》